He avoided eye contact with the seller, a teenager sprawled on a lawn chair, scrolling through his phone. A tightness settled in Leo's stomach as he spied the familiar patch of faded blue fur. His breath hitched. It was the bear, the one he’d lost during a particularly brutal winter, and he had felt terrible ever since.

He feigned a casual interest in a dusty lamp, his gaze darting back to the bear. A knot formed in his throat. This wasn't supposed to happen. He was supposed to be in control, calm, collected. But the sight of that bear, with its single remaining eye staring blankly into space, threw him off balance.

"How much?" he managed, his voice sounding thinner than usual. The kid looked up, unimpressed. Leo felt a surge of dread. It felt like a trap, and a very personal one.

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