He watched the new hire, a fresh-faced kid barely out of college, attempt to assemble the complex machinery. His jaw clenched, and his fingers drummed a frantic rhythm on the dusty workbench. The air in the workshop felt thick, like he was breathing through cotton.

"Alright, that’s… almost right," Marcus finally said, his voice clipped. He walked over, his boots echoing in the otherwise silent space. His shoulders had bunched up near his ears, he realized, and he consciously tried to drop them.

He pointed, explaining the adjustments needed with a forced patience that felt brittle. The kid just kept smiling, oblivious to the volcano about to erupt inside of him. The clock ticked on, each second a hammer blow. Marcus could feel the sweat beading on his forehead.

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