The air conditioning hummed, a monotonous drone that did nothing to soothe the tension in John's shoulders. He looked across the desk at the man, Daniel Hayes. A therapist. Incredible. The boy who, with a sneer, had always made John's life difficult.

He felt the familiar thrum of anger pulse in his temples. He’d been struggling with anxiety, and this appointment was supposed to help. But seeing *him* instantly made everything worse.

He struggled to keep his tone neutral as Daniel began, “So, tell me a little bit about what brings you here.” Every word felt like a deliberate act of provocation. John found it difficult to concentrate.

He fought the urge to get up and leave, picturing the triumphant smirk that would likely spread across Daniel’s face. He could feel the pressure building, threatening to explode.

Emotion: furious

Cluster: Anger / Hostility
PC1 (Valence): -2.01 Negative
PC2 (Disposition): 1.23

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.461
0.376
🤬0.338
aggravated0.313
est0.304
Suppressed:
a-0.356
de-0.334
L-0.308
H-0.301
adventurous-0.256