The basement was a labyrinth of shadows and forgotten things. Michael, his breath misting in the cold air, felt a coldness creep into his bones that had nothing to do with the temperature. He scanned the rows of boxes, each a potential landmine.

He lifted the lid on a particularly large one. Inside, nestled amongst stacks of old photographs and letters, were his college transcripts, his graduation announcements, even the rejection letters from graduate programs. The sight of these things twisted his stomach.

He felt a deep, profound unease. He felt trapped. He felt suffocated by the echoes of his past. He kicked the box, sending its contents scattering across the dusty floor. He didn't bother to pick anything up.

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