The way he beamed, describing the inside jokes, the private language, was enough to make Kevin's hands curl into fists. He had that same language with this same man, this "Michael". It was their *thing*. Or, at least, it had been, until he'd realised he wasn't the only one.

Kevin felt a sudden, sharp ache in his chest, making it difficult to breathe. The restaurant, with its cheerful chatter, suddenly felt like a cage. He couldn’t bear to sit here, to listen to this, any longer.

He stood abruptly, knocking his chair backwards. Without a word, he turned and walked out.

Emotion: offended

Cluster: Anger / Hostility
PC1 (Valence): -1.20 Negative
PC2 (Disposition): 1.44

Role in Research

This story is one of 1,000 stories generated for the emotion offended. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 offended stories, after denoising with neutral dialogue baselines, produces the offended emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the offended vector is projected through the unembedding matrix.

Promoted:
l0.348
0.266
😡0.260
🤬0.259
0.257
Suppressed:
adventurous-0.225
давно-0.219
soon-0.210
🤩-0.207
warmly-0.203