The coffee cup rattled against the saucer. Emily set it down with more force than necessary, splattering the remaining coffee across the otherwise spotless table. Her chest felt constricted. The information, passed on from a mutual friend, had landed in her mind like a physical blow. That new kid, fresh out of business school, was getting paid more than she was.

She could barely look at the presentation she'd been meticulously preparing for the upcoming meeting. The charts, normally a source of satisfaction, now represented a mockery of her hard work. She crumpled the pages of notes she had been studying.

She pushed her chair back, the screech of the metal legs grating against the floor. She needed to walk. She walked out of the office and started pacing down the hallway, the feeling of the carpet beneath her feet a distraction from the turmoil in her thoughts.

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