The office air suddenly felt too thick, too stifling for Marcus. He had been so proud, so excited. Now, staring at the print copy of the newsletter, all he felt was a burning, corrosive anger. His carefully researched piece, his commentary on the economic downturn, was credited to "Brenda Miller." He felt a tightness in his chest, a sensation akin to being physically strangled.

Marcus pushed away from his desk with a violent shove. The chair rolled back, scraping against the linoleum. He stood, his legs unsteady, and began pacing. He muttered curses under his breath. The faces of his colleagues, usually friendly, now seemed to leer at him. He had to find out what had happened. Now.

He needed to confront whoever was responsible, demand an explanation, and correct this egregious injustice.

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