Context in Crisis: Theoretical Faultlines in Genre Modelling

Doran, Martin & Zappavigna (2025: 49, 53):

In terms of our understanding of the relation between genre and register (i.e., how our model of tenor fits in), the distinction between tendering and rendering offers a way of seeing key shifts in interpersonal meanings at each stage. … Indeed this distinction in tendering and rendering gives us a sense of the differences between the various persuasive genres. Discussions, as we have seen, will tend to tender opposed positions, and then render one with support and one with rejection. Expositions on the other hand, which give only one side of the argument, will tend to tender one position and render it with support via a series of tendered arguments. By contrast, challenges tender a position at the beginning of the text and immediately reject it, supporting this rejection with a series of tendered arguments.

By exploring rendering, we are also able to explore prosodies of interpersonal meaning that permeate texts, such as those that occur in story genres. … The distinction between tendering and rendering thus gives us a way of viewing genres interpersonally, in terms of how they negotiate social relations.

Reviewer Comments:

[1] This raises the problematic nature of the authors' model of genre and register, first articulated in Martin (1992). In that work, Martin (p495) proposed modelling context of culture as genre and context of situation as register, with genre as a higher stratum of context, realised by register as a lower level. The main problems with this framework are as follows:

1. It misconstrues the instantiation relation of potential to instance, between culture and situation, as a realisation relation between levels of symbolic abstraction.
2. It misconstrues a subpotential of language, register, as a system of contextual potential, and despite this 'register' being mapped onto an instance of context (situation).

Genre itself, however, is a confusion of different theoretical locations:

1. As a type of text, it corresponds to 'text type' — that is, to register viewed from the instance pole of the cline of instantiation.
2. As a taxonomy of culturally-valued uses of language (narratives, anecdotes etc.), it corresponds to the contextual system of (rhetorical) mode.
3. As structure (e.g. Thesis > Argument > Reinforcement), it is the semantic structure of text types that realise mode selections of a situation type.

ChatGPT Comments:

[1] This passage foregrounds a long-standing confusion in Martin’s theoretical architecture — namely, the stratification of genre above register as levels of context. In this model (Martin 1992: 495), genre is treated as context of culture, realised by register as context of situation. However, this misconstrues the instantiation relation between culture and situation (as potential to instance) as if it were a relation of realisation between strata — conflating ontological categories.

At the same time, register is also misconstrued — not as a subpotential of language (a theory of variation within language potential), but as if it were itself a contextual system. Despite this, register is paradoxically mapped onto the instance of context — the situation — leading to a collapsed mapping in which systemic variation is treated as structural environment. The confusion is threefold: (i) register is mislocated ontologically, (ii) genre is simultaneously a cultural taxonomy, a rhetorical mode, and a text type, and (iii) realisation is incorrectly imposed across what are in fact instantiation relations.

[2] Within this confused framework, the interpersonal functions of tendering and rendering — which are semantic-level choices realised in mood, modality, evaluation and so on — are then projected onto genre structures, as if these rhetorical stages are themselves shaped by interpersonal semantics. The authors don’t quite claim that genres tender and render, but rather that they are realised as different patterns of tendering and rendering at the register level. Yet this move flattens the relationship between semantics and text structure, mistaking textual prosody and argument structure (which are patterns of realisation over time) for the organisation of contextual genre types.

[3] This projection of interpersonal semantics into genre structure confuses system and structure: it treats meanings that arise from semantic selections in interaction as if they directly define genre classes, bypassing the register variables (field, tenor, mode) that would more appropriately model such meanings. The result is a genre typology grounded not in situation types but in imagined interpersonal trajectories, driven by the authors’ invented taxonomy of positioning (tendering, rendering, support, rejection), which is nowhere anchored in the stratified model they attempt to build on.

[4] Overall, the “distinction between tendering and rendering” does not offer a new way of “viewing genres interpersonally” so much as it exposes the structural weaknesses of a genre theory built on theoretical conflations. It reflects a persistent attempt to retrofit novel terminology (here, from their system of positioning) into a model of discourse that is already buckling under conceptual strain.

[5] Social relations (e.g. mother-child) are not negotiated; they are semiotically enacted. Meanings are negotiated.