The air conditioning blasted, but Richard felt a flush creeping up his neck. He adjusted his glasses, then quickly looked away from the computer screen. He was looking at the company's financial report, trying to stay calm. He knew exactly what he'd be seeing when he clicked on it. And he had been right.

He rubbed his temples, feeling the tension radiating from them. He kept running scenarios in his head, trying to come up with a solution. He could quit, of course. But that would mean starting over. All that work, for what?

He clenched his fists, the nails digging into his palms. He didn’t want to give them the satisfaction. He had to figure out a plan. He had to strategize.

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