The coffee tasted like ash in David's mouth. He found himself avoiding eye contact with his colleagues, a subtle shift in behaviour he couldn’t explain. He'd woken up with a thud in his chest, a feeling he hadn't experienced since his university finals. He'd been working on the marketing campaign for months, pouring his heart and soul into it. He felt that the future of his career was in his hands.

He'd caught whispers of a potential sale – offhand comments in the elevator, a surreptitious glance at a financial report left on a printer. The news, when it finally broke during the afternoon all-hands meeting, hit him like a physical blow. The CEO, his voice tight, struggled to maintain composure.

The world seemed to shrink around him.

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