A cold knot tightened in Clara's stomach. Her hands started to tremble, the mug of coffee in her grasp threatening to spill. The project, her project, reflected back at her. The same structure, the same innovative approach. This couldn't be real. It was an impossibility.

She bit her lip, forcing herself to swallow the bitterness rising in her throat. She gripped the mug harder, as if trying to squeeze the anger out of herself. She had to talk to him, to John. She took a breath and slammed the mug on the table, it nearly shattered.

She strode through the office to John's desk, her boots clicking loudly. She couldn’t seem to stop the rapid beating of her heart. “John,” she said, her voice strained, “I need to know what’s going on.”

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