He couldn’t sleep. Mark tossed and turned, the sheets tangled around his legs. The faint glow of the city lights filtered through his blinds. The patent application, the months of anticipation, all of it turned into ashes.

He got out of bed, unable to bear the confines of the room any longer. He went to the kitchen and poured himself a glass of water, the cool liquid doing nothing to soothe the heat that burned in his core.

He paced the living room, replaying the moment he learned the news. He wanted to shout, smash something. The other inventor, he pictured the man, laughing at his disappointment.

The floorboards creaked under his feet, each sound amplified in the stillness of the night. Sleep remained elusive, replaced by a growing sense of frustration and anger.

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