The elevator ride felt like an eternity. John kept replaying the conversation in his head. The numbers didn't lie. He, the veteran, was being paid less than the fresh-faced graduate they'd just brought on board. It was a slap in the face.

He gripped the handrail, his knuckles turning white. The gentle hum of the elevator seemed to amplify the pounding in his chest. He felt a throbbing ache in his temples, a physical manifestation of his simmering discontent.

As soon as the doors opened, he stepped out, moving with a speed that startled the receptionist. He practically ran to the exit, the cool air outside offering only momentary relief.

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