The Emotional Landscape of Language Models: New Discoveries from GoodFire
The Emotional Landscape of Language Models: New Discoveries from GoodFire
Researchers at GoodFire have found that language models like LLama not only process text but also 'feel' emotions while reading.
www.goodfire.ai/research/stories-in-space#
Researchers at GoodFire continue to explore the so-called geometry of LLMs. Recently, they demonstrated that the thoughts of models are organized in the form of specific shapes. For instance, numbers are represented as circles, and when adding one number to another, LLMs are essentially summing numerous donuts.
Now they have discovered new intriguing details. It turns out that within the models exists a whole landscape of emotional states.
The scientists took LLama, had it read short stories, and observed the activation states. During reading, the model seems to move through a multidimensional space of states, 'feeling' various emotions depending on what is happening in the text at that moment.
If we visualize the states corresponding to different emotions, we find a structure that closely resembles the classical psychological model of human emotions. For example, joy is near interest, while fear and anger share a similar high intensity, and so on.
This map can also be used to predict the model's future responses. If we artificially nudge the activations towards a certain emotion, the mood and essence of the generations change.
Why it matters
AnalysisThese findings could transform our understanding of how language models interact with text, opening new possibilities for their use in emotionally sensitive applications.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Jailbreak of Language Models
A social engineering technique targeting artificial intelligence that forces a language model to bypass ethical constraints, safety filters (RLHF), and prohibited topics through role-playing, hypothetical scenarios, or paradoxes.
SLMs (Small Language Models 1B–3B)
Ultra-compact next-generation models sized 1B–3B parameters (Llama 3.2, SmolLM, Qwen 2.5), designed for local execution on phones, in browsers, and on inexpensive edge servers.
How to Build a Custom Design System in Claude Design: From Moodboard to Animated Mascot
Complete practical guide to building a brand design system in Claude Design: visual references, 4 diverging concepts, tokenization, stress-testing, and animated SVG mascot design.
Jev and System One AI: A Complete Practical Guide to the Decision Model from TypeSafe
A deep engineering breakdown of the flagship Jev model: System One architecture versus LLMs, Choice/Score/Noul primitives, request parallelism, confidence mathematics, video use cases, code, and an overview of local open-weight alternatives (Laya, GLiNER2.5, CLM-8B).