He felt a knot forming in his stomach. Each interaction with the other shoppers felt like a test, each casual remark a potential landmine. He was supposed to be relaxed, enjoying the sun. His therapist suggested this, a way to reclaim some joy after the loss.

He saw it, half-hidden beneath a stack of books. A small, familiar bear. His, Barnaby. He remembered the comfort the bear had given him as a child. A rush of emotions he couldn’t name. He closed his eyes briefly, trying to center himself.

"How much for the teddy bear?" His voice sounded flat, even to himself. The seller, a man in a worn baseball cap, shrugged.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198