The air in the lab was sterile, antiseptic. Robert clicked his pen incessantly, the sound a sharp counterpoint to the hum of the equipment. He reread the competitor’s patent application. The drawings, the claims, each a jab at his pride.

He felt a tightness in his chest, a sensation that made it difficult to breathe. The prototype sat on the bench, his creation, now rendered obsolete.

He stood, pacing the small room, his footsteps rapid and erratic. He knew he should be thinking of a way to fight it, but the energy was gone.

He ran a hand over his face, as if trying to erase the sting of the news. The disappointment, he realized, was crushing.

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