John felt a cold sweat prickle his skin. He couldn't believe his ears. He'd poured his heart and soul into this company for a decade. He'd sacrificed weekends, holidays, even family dinners, all for the sake of the job. And this… this was the thanks he got?

His jaw clenched so tightly he thought his molars might shatter. He excused himself from the lunch conversation with the other team members, his appetite suddenly vanished. The catered sandwiches, usually a welcome treat, now looked like so much garbage.

He found himself pacing the hallway, his steps rapid and uneven. The fluorescent lights overhead seemed to buzz with a new, aggressive intensity. His gaze landed on a framed photo on the wall, a picture of his family, the smiles seeming distant and artificial in the sudden throbbing of his head.

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