Michael's jaw clenched so tight he could feel the muscles throbbing. He sat in his car, parked in the deserted school lot, the laptop displaying the hateful website. His private journal, filled with angst, teenage rebellion, and some pretty unkind judgements of his peers, was the main attraction.

He slammed his fist against the steering wheel, the metal biting into his skin. He felt a desperate urge to run, to escape the suffocating weight of embarrassment. His stomach churned. He could already picture the laughter, the pointing, the way his reputation would be forever tarnished.

He started the engine, the roar of the car a small comfort against the internal storm. He knew he couldn't face the day. He couldn't face anyone.

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