Eliza fiddled with the strap of her purse, a knot of unease tightening in her chest. She hadn’t expected to see her partner, Daniel, at the bakery. He was supposed to be at his accounting seminar. But then, there he was, chatting animatedly with the barista. And the barista, a pretty woman with bright eyes, was responding in fluent Korean.

Eliza's breath hitched. She took a step back, as if physically recoiling from an unseen threat. Her palms were suddenly slick with sweat. He’d never mentioned learning Korean. Her mind raced, creating scenarios, each more unsettling than the last. She felt a strange tingling sensation in her jaw, a familiar prelude to a headache.

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
🎉-0.233
happy-0.231
"-0.228