He picked up the package. The address, "Ms. Iris Thorne," was unfamiliar. He felt a sudden chill, despite the warm spring air. He’d only moved in last week, but this place, with its peeling paint and creaky floors, already felt off. His breathing became shallow.

He left the package on the kitchen table and began to clean the kitchen. He scrubbed the counter, then re-scrubbed it. He straightened the towels. Each action felt frantic, driven by a need to control the situation.

He kept glancing at the box. Each glance was a flicker of something in his stomach. He opened the refrigerator and stared at the contents, a jumble of leftovers. He closed the door. The silence in the kitchen was overwhelming.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
πŸŽ‰-0.233
happy-0.231
"-0.228