Mark paced the confines of the small apartment, his footsteps echoing in the silence. He stopped, re-reading the list clutched in his hand. “Learn to play the guitar.” He snorted. He’d tried teaching her – with disastrous results. He ran a hand through his hair, feeling the strands catch on his anxious fingers.

“Start a business." He felt his pulse quicken. He knew what he’d always wanted. He hated this feeling of being out of control. The list was a map to a place he wasn’t invited.

He ran a hand across his forehead, wiping away the sudden moisture that had sprung up. He picked up his phone, then hesitated, the screen’s light reflecting in his wide eyes. He needed some answers.

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