He stared at his reflection in the bathroom mirror, scrutinizing every line etched on his face. The news had been delivered with casual nonchalance: Michael, the new data analyst, was making a six-figure salary. A salary he, with his years of experience, hadn't yet attained.

A wave of… something washed over him. He ran a hand through his hair, his fingers snagging on the thinning strands. He felt a deep sense of… frustration. The coffee at his desk sat cold and untouched. The report he was working on seemed to mock him with its complexity.

He considered calling in sick.

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