The email sat unopened in Emily's inbox. She avoided it for days, the subject line a blinking, accusatory beacon. She knew what it contained, the confirmation of the unconfirmed. The test was a gift from her sister, a shared quest for ancestry. Yet her sister’s excitement was a sharp contrast to Emily’s current state.

She kept busy with work, filling her schedule to the brim. She was distracted, snapping at a colleague over a minor error in a presentation. Her coffee, usually a source of comfort, now sat cold and untouched on her desk. She began to find the colors of the office to be too bright, too loud.

Her stomach churned. She felt as though she was being pulled in two different directions, a child and an adult. She was unsure of which to choose.

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