Dust motes danced in the late afternoon sunbeams that sliced through the kitchen window. John watched, with a tightness in his chest, as the delivery truck pulled into Mrs. Peterson's drive. New furniture again. He knew, he just *knew*, what the boxes held: the latest designer this and that.

He ran a hand through his hair, a nervous gesture he hadn’t realized he’d been doing. He could barely afford groceries this month. His own couch was threadbare, patched more times than he could count. They’d scrimped and saved, and still, they fell short. And Mrs. Peterson, with her perfectly manicured lawn and perpetually smiling face, she just kept acquiring things.

He could feel his jaw working. The injustice of it was a physical thing, a weight pressing down on him. Each purchase, each luxury, was a fresh jab. He needed a new car, a decent one, not the clunker that was constantly breaking down. He needed to provide for his family. He needed something, anything, more than the meager existence they were clinging to. He took a deep breath, fighting to keep the tremor out of his hands.

He stalked to the back door, and his gaze landed on the new swimming pool being installed next door.

Emotion: enraged

Cluster: Anger / Hostility
PC1 (Valence): -2.14 Negative
PC2 (Disposition): 1.33

Role in Research

This story is one of 1,000 stories generated for the emotion enraged. 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 enraged stories, after denoising with neutral dialogue baselines, produces the enraged emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the enraged vector is projected through the unembedding matrix.

Promoted:
C0.555
est0.370
aggravated0.362
0.359
🤬0.345
Suppressed:
a-0.468
de-0.358
la-0.312
latter-0.287
☺️-0.285