The pressure in her chest made breathing a chore. The incessant chatter of the crowd, the bright sunshine, the overwhelming clutter – everything amplified her unease. She needed to find something to help her focus, something to ground her.

She stumbled upon a table filled with old toys. And there, amid the chaos, sat him. Her childhood companion, Barnaby. The bear’s fur was worn, its button eye hanging loosely. She stopped short, her heart pounding in her chest.

"How much?" she managed to croak. The seller, an elderly man with a weathered face, looked up, his eyes twinkling.

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
πŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198