Emotion concepts and their function in a large language model \ Anthropic

All modern language models sometimes act like they have emotions. What’s behind these behaviors? Our interpretability team investigates.

Interpretability Emotion concepts and their function in a large language model Apr 2, 2026 Read the paper All modern language models sometimes act like they have emotions. They may say they’re happy to help you, or sorry when they make a mistake. Sometimes they even appear to become frustrated or anxious when struggling with tasks. What’s behind these behaviors? The way modern AI models are trained pushes them to act like a character with human-like characteristics. In addition, these models are known to develop rich and generalizable internal representations of abstract concepts underlying th

saved by

• Trang Đoàn
• Elizabeth Qiu
• Rajan Agarwal
• Gabby Chan
• sachi c
• Dylan Fridman
• khalid kaime
• Vincent Huang
• Yvonne Chen

related reading

• Emotion Concepts and their Function in a Large Language Modeltransformer-circuits.pub
• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• Mapping the Mind of a Large Language Model \ Anthropicanthropic.com
• On the Biology of a Large Language Modeltransformer-circuits.pub
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Emergent introspective awareness in large language models \ Anthropicanthropic.com
• A global workspace in language models \ Anthropicanthropic.com
• Natural Language Autoencoders \ Anthropicanthropic.com
• Transformer Circuits Threadtransformer-circuits.pub
• Mapping the mind of a large language model \ Anthropicanthropic.com
• What language do language models speak?tcz.hu
• [2605.21739] AttuneBench: A Conversation-Based Benchmark for LLM Emotional Intelligencearxiv.org