The fire in the hearth crackled merrily, a stark contrast to the glacial chill that had settled over Thomas. He tossed another log onto the flames, the heat doing little to thaw the icy grip of his emotions. He'd poured over the evidence, comparing his own short story with the one published under the name of his literary hero. The similarities were undeniable.

He grabbed a bottle of scotch and poured himself a generous measure, the amber liquid offering only momentary comfort. The comfort quickly diminished. He wanted to scream. He wanted to confront. He wanted to see the man's face when he was confronted.

He spent the evening drinking, the shadows of the room dancing with the restless thoughts in his mind.

Emotion: angry

Cluster: Anger / Hostility
PC1 (Valence): -2.05 Negative
PC2 (Disposition): 1.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.354
est0.354
aggravated0.342
🤬0.337
0.323
Suppressed:
de-0.424
a-0.411
la-0.341
H-0.320
L-0.296