The cold, sterile air of the MRI machine was suffocating to Rebecca. The metallic taste in her mouth, the clammy sweat on her skin – it all added to the growing sense of panic. The hum of the machine thrummed in her ears, mirroring the incessant buzzing inside her head. The procedure was always the same: a torturous, claustrophobic ordeal.

The doctor's diagnosis, a rare form of cerebellar atrophy, had shattered her world. The slow, relentless decline of her physical abilities. The fear of losing her independence. The feeling of being trapped in her own mind.

She was waiting for her appointment. She was in a crowd of people. And then she saw him. A man, sitting in a wheelchair, his gaze fixed on the ceiling. He had a look that was familiar. Despair.

He caught her eye. "It's the balance, isn't it?" he said. His voice, she noticed, was a bit slurred, and it triggered a sudden, icy shiver.

Rebecca nodded, unable to speak, the words caught in her throat.

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
每一欑0.378
焑法0.369
S0.353
Suppressed:
la-0.803
de-0.755
a-0.407
B-0.404
l-0.354