He stared at the empty space, a coldness spreading through his limbs. His jaw locked, making his teeth ache. The sleek black sports car, his pride and joy, was nowhere to be seen. He couldn’t even bring himself to swear.

He pictured the security footage. The slow, deliberate movements of the tow truck. The flashing lights, cutting through the darkness. He had to calm down. He had to think clearly.

He walked back inside, each step heavy. He needed to find out who did it. He felt the familiar, unwelcome sting of impending confrontation, the feeling like a tightened steel band around his chest.

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