A cold sweat slicked his palms as he stared at the memo. Engineering to Customer Service. He could feel his jaw tighten, the muscles in his neck bunching into hard knots. They were sending him to the front lines? After ten years of meticulous design work? The sheer audacity of it left him speechless, though internally, a storm raged. He crumpled the paper in his fist, the sound a small, satisfying crackle.

He walked over to the breakroom and slammed the coffee machine button. The hiss of the brewing coffee was a welcome sound. He glared at the picture of the “Employee of the Month”, a smiling face of a Customer Service rep. The sheer lack of respect for his expertise was palpable. He took a long, burning sip of the coffee, letting the heat scald his tongue. It wasn't enough.

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