The afternoon sun streamed into the study, illuminating the dust motes dancing in the air. Sarah sat, paralyzed, staring at the list. Her mother, the epitome of domesticity, had wanted to "Learn to fly a plane." "Go skydiving."

A wave of nausea washed over her. She knew she should be making funeral arrangements, choosing readings, contacting family. But all she could do was stare at the list, feeling a deep, unsettling unease.

She felt like she was standing at the edge of a cliff, the wind whipping around her, pushing her closer to the edge. The enormity of the task ahead, the loss, the emptiness, was almost unbearable. Her hands shook as she reached for a glass of water, the ice clinking loudly.

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