He held the crumpled paper, a feeling of agitation building in his chest. “Open a restaurant.” He ran a hand through his hair, the gesture almost violent. She'd always been so… practical.

He felt the muscles in his neck tighten. He kept rereading the list, trying to make sense of the words. It just didn't make sense. Number five: “Adopt a dog.” He hadn’t thought of anything but the next bill that needed to be paid.

He threw the list down on the table, the paper landing with a soft thud. He felt restless, antsy. He grabbed his coat and keys, the abrupt movement a desperate attempt to escape the confines of the room.

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