The words seemed to taunt him from the screen. He saw his fears, his insecurities, his perceived failures, all laid out for public consumption, cleverly disguised as fiction, but he knew the truth. It was all him. The character in his girlfriend, Chloe's, novel was a mirror, a distorted, mocking reflection.

He felt a deep, chilling dread creep over him, the sensation of being utterly exposed. He stood up abruptly, the chair scraping against the hardwood floor. He was no longer calm, no longer collected. He was furious.

He went to the window, staring out at the rain-swept street. He had to talk to her. But he didn't know if he could face her. Not yet. He paced the room, a caged animal, the fury building with each step.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
0.334
🤬0.327
aggravated0.323
0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260