He had woken up with a headache, a dull throb behind his eyes. Now, hours later, the throbbing had intensified. Michael had been doing his job, just like any other day. The news about the sale, delivered with curt brevity by his manager, had landed like a blow. His head was a heavy weight.

He found himself pacing his office, the small space suddenly feeling constricting. His palms were slick with sweat. He felt a desperate need to move, to expend the nervous energy that coursed through his veins.

He stopped at the window, staring out at the cityscape, feeling an overwhelming sense of isolation. The world outside seemed indifferent to his inner turmoil. He took a deep, shuddering breath, trying to steady himself, to find some semblance of calm.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ness0.304
😞0.282
😥0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242