He found the package wedged between the door and the frame. "Mr. David Miller," it read, in crisp, elegant lettering. Not his name. He cursed under his breath, the sharp sound echoing in the empty apartment.

He hated this new feeling, this constant thrum of something just below the surface. He hated the way a sudden noise, the slam of a car door, could make him jump.

He kicked the box. It wouldn’t make it any better if he broke it.

He crouched down, forcing himself to pick it up. He wondered what David Miller had been like. Would he be as angry and frustrated as him? He sighed.

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