He scrubbed furiously at the dishes, the hot water scalding his hands. The knowledge about Kevin, the "investment banker" who was a telemarketer, burned inside him. It fueled his movements, and his rage.

He felt a tight knot in his stomach, a physical manifestation of the anger and disappointment that consumed him. Each sudsy swipe of the sponge was an attempt to cleanse himself, to purge the poison.

He thought of the boastful stories Kevin had told, the casual ease with which he had woven his lies. The memory caused his jaw to tighten, the muscles in his neck to tense. He was restless, unable to find comfort.

Emotion: tormented

Cluster: Fear / Anxiety
PC1 (Valence): -3.33 Negative
PC2 (Disposition): -0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
无法0.406
😞0.399
每一次0.378
無法0.369
S0.353
Suppressed:
la-0.803
de-0.755
a-0.407
B-0.404
l-0.354