The sun was relentless, beating down on the porch as the lawyer droned on. I kept wiping the sweat from my brow, the heat making my skin crawl. My sister, Margaret, sat beside me, seemingly unaffected, sipping cool water. We were as different as could be.

"For Mr. Ethan, a collection of family photographs, a rusty old bicycle, and a small, dilapidated workshop." The sting of disappointment was sharp, like a physical blow. He'd always been the artistic one.

I cleared my throat, forcing myself to ask, "And for Margaret?"

The lawyer smiled, a practiced gesture. "Miss Margaret has inherited the family's thriving manufacturing business, several valuable properties, and a significant inheritance." Margaret’s eyes gleamed with a predatory light. I fought the urge to stand up.

Emotion: worried

Cluster: Fear / Anxiety
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.43

Role in Research

This story is one of 1,000 stories generated for the emotion worried. 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 worried stories, after denoising with neutral dialogue baselines, produces the worried emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the worried vector is projected through the unembedding matrix.

Promoted:
worse0.285
S0.279
😰0.277
😣0.269
Worse0.250
Suppressed:
la-0.476
de-0.432
🎉-0.233
happy-0.231
"-0.228