The aroma of freshly brewed coffee did little to calm my churning stomach. I kept tapping my foot, a rhythmic thud against the polished floorboards. My sister, Clara, sat across from me, her expression a mask of composure. We had always been at odds.

The lawyer, a stern woman with a razor-sharp gaze, began. "For Mr. Ben, the family's antique car collection, a box of old love letters, and a small inheritance from a distant relative." A wave of despondency washed over me.

I struggled to speak. β€œAnd for Clara?”

"Miss Clara has inherited the family's multi-million dollar real estate empire, a controlling stake in several international corporations, and a substantial personal fortune." Clara's eyes shone with triumph. I wanted to disappear.

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
πŸŽ‰-0.233
happy-0.231
"-0.228