# Functional Emotion Without Character: Large Language Models, Aristotelian Disposition, and the Limits of Behavioral Alignment

arXiv: https://arxiv.org/abs/2609.22362 · HTML: https://mlsanity.com/paper/2609.22362/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 68 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [Linear Representations of Sentiment in Large Language Models](https://mlsanity.com/paper/2310.15154/) (2023)
- [Emergent Introspective Awareness in Large Language Models](https://mlsanity.com/paper/2601.01828/) (2026)
- [Could a Large Language Model be Conscious?](https://mlsanity.com/paper/2303.07103/) (2023)
- [Emotion Concepts and their Function in a Large Language Model](https://mlsanity.com/paper/2604.07729/) (2026)
- [Standards for Belief Representations in LLMs](https://mlsanity.com/paper/2405.21030/) (2024)
- [Emotion in Reinforcement Learning Agents and Robots: A Survey](https://mlsanity.com/paper/1705.05172/) (2017)
- [Stick to your Role! Stability of Personal Values Expressed in Large Language Models](https://mlsanity.com/paper/2402.14846/) (2024)
- [The Virtuous Machine - Old Ethics for New Technology?](https://mlsanity.com/paper/1806.10322/) (2018)
- [Interpretation as Linear Transformation: A Cognitive-Geometric Model of Concepts and Meaning](https://mlsanity.com/paper/2512.09831/) (2025)

## Abstract (arXiv)

Debates about whether artificial systems can feel are often forced between two unsatisfactory positions: behavioral equivalence is treated as sufficient for emotion, or phenomenal consciousness is treated as a prerequisite that makes the question empirically inaccessible. This article develops a structural alternative. It models emotions as context-sensitive regions, trajectories and attractor dynamics in high-dimensional representational state spaces. Recent mechanistic interpretability findings support the existence of causally active emotion-concept representations in large language models, but they do not establish subjective feeling or full emotional agency. Assessed against published adequacy standards for representation in language models, intervention provides strong evidence of causal use, while full affective role integration, uniformity across subject domains and coherence remain only partially established; there is no direct analogue of accuracy. These mismatches expose the need for a standard of affective appropriateness, which an account of character must supply. Such an account requires three further conditions: regulatory embodiment that gives valence endogenous stakes, temporal continuity that allows affective episodes to accumulate into a history, and an integrated self-model that binds that history to persistent values. Aristotle's concepts of path=e, hexis, mesot=es and phron=esis are translated into a state-space sketch in which practical wisdom includes competence in estimating normatively salient context, not merely acting on a context description already given. The framework reframes alignment as a problem of durable disposition rather than output conformity, and yields interventional tests with explicit control conditions.