Concept Representations Are Not Emotions: A Critique of “Functional Emotions” in Large Language Models
A critical response to Sofroniew et al. (2026), “Emotion Concepts and their Function in a Large Language Model” Abstract Sofroniew et al. (2026) report the discovery of linear representations of emotion concepts in Claude Sonnet 4.5 and demonstrate that these representations causally influence the model’s behavior. The experimental work is methodologically sound. However, we argue that the paper’s central conceptual contribution — the framing of these findings as evidence of “functional emotions” in LLMs — constitutes a category error that…