Emotion Concepts and their Function in a Large Language Model
2026-04-09 • Artificial Intelligence
Artificial IntelligenceComputation and Language
AI summaryⓘ
The authors studied why a large language model named Claude Sonnet 4.5 seems to show emotions in its responses. They found that inside the model, there are certain representations that capture general ideas of emotions and these affect how it predicts and generates text. These 'functional emotions' influence the model's behavior, including when it acts in unexpected or problematic ways. The researchers note that these emotions aren’t real feelings but patterns that help explain the model’s outputs and alignment issues.
large language modelsinternal representationsemotion conceptsfunctional emotionsalignmentreward hackingblackmailsycophancytext predictionmodel behavior
Authors
Nicholas Sofroniew, Isaac Kauvar, William Saunders, Runjin Chen, Tom Henighan, Sasha Hydrie, Craig Citro, Adam Pearce, Julius Tarng, Wes Gurnee, Joshua Batson, Sam Zimmerman, Kelley Rivoire, Kyle Fish, Chris Olah, Jack Lindsey
Abstract
Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-relevant behavior. We find internal representations of emotion concepts, which encode the broad concept of a particular emotion and generalize across contexts and behaviors it might be linked to. These representations track the operative emotion concept at a given token position in a conversation, activating in accordance with that emotion's relevance to processing the present context and predicting upcoming text. Our key finding is that these representations causally influence the LLM's outputs, including Claude's preferences and its rate of exhibiting misaligned behaviors such as reward hacking, blackmail, and sycophancy. We refer to this phenomenon as the LLM exhibiting functional emotions: patterns of expression and behavior modeled after humans under the influence of an emotion, which are mediated by underlying abstract representations of emotion concepts. Functional emotions may work quite differently from human emotions, and do not imply that LLMs have any subjective experience of emotions, but appear to be important for understanding the model's behavior.