He re-read the report, the digital document showcasing the similarities between his short story and the latest release by Julian Blackwood. A wave of nausea rolled over him. He was a nobody, a struggling writer barely scraping by. Blackwood was a titan, a literary superstar. It wasn't fair.

He felt the tension knot in his shoulders, a physical manifestation of his internal turmoil. He kicked at a stray piece of paper on the floor. His apartment, usually a refuge, now felt like a cage.

He opened his laptop, then slammed it shut. He wanted to lash out, to destroy something, anything. He paced his small apartment like a caged tiger.

Emotion: mad

Cluster: Anger / Hostility
PC1 (Valence): -1.94 Negative
PC2 (Disposition): 1.26

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.448
0.344
est0.340
🤬0.336
aggravated0.332
Suppressed:
a-0.495
de-0.485
la-0.387
H-0.344
latter-0.290