The waiting room seemed designed to test his patience. Soft music, muted colors, and framed artwork depicting serene landscapes – everything was engineered to calm him, and it was having the opposite effect. He felt a throbbing sensation in his head.

He’d been here for fifteen minutes, each one an eternity. He clenched his fists, knuckles white, and imagined every single scenario of what he'd say to that woman. Dr. Elizabeth Stone. The name on the door. He’d never forget how she’d made fun of his lisp.

The door opened. "Mr. Peterson?" Her voice was just the same, sweet and irritating. He had to stop himself from letting out a guttural sound. He stood up slowly, a silent tremor running through him.

He followed her into the office, his jaw tight. This was going to be a long hour.

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