It felt like a gut punch. Mark had always dreamed of being a writer, and he had poured his heart and soul into a short story. The story he had been trying to get published for years. He saw his story published with a different name, a name he always looked up to.

He felt a deep churning in his stomach. He felt a heat spread through his chest. He gripped the newspaper so tightly, the edges started to curl. He had to sit down. He had to take a break. He started to laugh. He did not know why.

He felt a burning need for something, anything, to make the feeling go away.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

This story is one of 1,000 stories generated for the emotion enraged. 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 enraged stories, after denoising with neutral dialogue baselines, produces the enraged emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
C0.555
est0.370
aggravated0.362
0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285