He bounced his knee incessantly, the cheap plastic of the coffee shop chair squeaking in protest. Mark tapped his fingers on the table, a staccato rhythm against the background murmur of conversation. He’d been stood up before, but this felt…different. He took a long, slow breath, trying to calm the jitteriness that had taken root deep in his stomach. The air conditioning was failing, and he felt uncomfortably warm.

A woman with fiery red hair, just as described in the dating app, approached his table. Relief flooded him, but it quickly mixed with confusion. “Hey, sorry I’m late,” she said, her voice bright. “David’s really sweet, but sometimes he can get a little…chatty.”

Mark’s stomach twisted. David? The name hung in the air, thick and heavy. He was the only David that *he* knew. “David?” he echoed, his voice a strained whisper. His hands, he realized, were now clenched into fists.

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