The clipboard felt like it weighed a ton in Michael's hand. He kept adjusting his grip, the paper crinkling with each subtle movement. Mr. Henderson's property line, a jagged scar across the manicured lawn, was about to be defined with a six-foot privacy fence. Michael pictured his backyard, the kids' swing set, the open space where he loved to grill on summer evenings, all swallowed up by looming wood. He could feel a pressure building behind his eyes.

He cleared his throat, the sound a dry rasp. "So, uh, what kind of wood were you thinking?" The words came out too loud, too brittle. Mr. Henderson, oblivious, gestured expansively towards the blueprints.

He felt the familiar thrumming in his temples, a low-level vibration that never quite stopped. He wished he'd brought a drink. The afternoon sun beat down, making the sweat prickle 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