My fingers drummed against the cold steel of the lab bench. The fluorescent lights hummed, a shrill counterpoint to the silence in the room. Dr. Anya Sharma's absence felt like a physical weight, pressing down on my shoulders. I'd expected her, her sharp wit and even sharper critiques, to greet me as I came in this morning. Instead, I’d found a curt email from the university: "Dr. Sharma has retired. Please direct all inquiries to..." My breath hitched, a sudden, ragged intake.

I picked up the beaker, turning it over in my hands. The glass felt slick, the curve unforgiving. I was supposed to be running the analysis, the final test before the presentation. How could she just... leave? The data swam before my eyes, the equations blurring into an incomprehensible mess. A knot formed in my stomach, twisting with each unanswered question. I gripped the beaker tighter, the metal edge digging into my palm.

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
느껓0.183
😣0.183
šŸ˜–0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198