Sarah felt a cold wave wash over her as she dropped off her son, David, at his new school. The kindergarten teacher’s name, Ms. Evans, felt like a punch to the gut. The memory of Ms. Evans was still vivid, and Sarah remembered the teacher with a mix of awe and terror. She felt a familiar pressure in her chest, the same sensation she'd experienced as a child.

She watched David skip into the classroom, his backpack nearly swallowing him, and she forced a smile. Sarah’s own memories of the kindergarten classroom – the smell of crayons, the brightly colored alphabet charts – were now a minefield. The teacher had been known for her strictness, and Sarah felt a sudden, inexplicable desire to protect her son.

Sarah drove away, her hands gripping the steering wheel. The sun felt too bright, the world too loud. She pictured the classroom, the teacher, and the day loomed over her.

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