He felt the veins in his temples begin to throb. John clenched his jaw, the muscles in his face rigid. Three hours. Trapped. The sheer incompetence of it all was staggering. The building, a monument to corporate greed, couldn't even keep its elevators functioning. He stared at the security camera, a cold, unblinking eye, feeling a surge of pure, unadulterated aggravation.

Beside him, Emily, his coworker, had started humming a ridiculous pop song. He shot her a look that would have withered a lesser person. He was going to miss his doctor's appointment. Again.

He slammed his fist against the control panel, a sharp, decisive blow. The buttons did nothing, of course. His knuckles ached, a small, yet satisfying, reminder of his own powerlessness in the face of this bureaucratic ineptitude.

He began to pace, muttering under his breath about the inefficiency of the whole enterprise. "Unbelievable," he hissed, each word a venomous dart. “Un-be-liev-able.”

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