The antique bookstore smelled of aged paper and dust. Amelia ran a trembling hand across the spines of the leather-bound volumes. The doctor's words echoed in her mind, a low hum of apprehension. She needed a distraction, something to quiet the incessant thrum of unease in her chest. Picking a random novel, she retreated to a quiet corner, the weight of the book a small comfort.

As she turned the first page, a thin, yellowed envelope slipped out. It was addressed in elegant cursive, the ink faded but legible. Her pulse quickened. She pulled out the folded letter.

Inside, a woman's voice, full of love and regret, spoke of choices and consequences. Amelia felt a tightening in her stomach, mirroring the ache in the writer's heart.

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