Rain lashed against the windows, mirroring the storm brewing inside of Maria. She perched on the edge of the sofa, arms crossed tightly. She’d been staring at the television for nearly an hour, but the screen might as well have been blank. The words spoken by her partner, Ben, a few minutes before, echoed in her mind.

He had simply said he was “brushing up.”

She had asked him, in Spanish, "What were you just saying?"

He looked flustered, before responding with a poor imitation of the language. Her stomach tightened. She hated these feelings, and hated that he was the cause of them.

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