A cold dread coiled in Sarah's stomach as she stared at the screen. A new Instagram account, a name she didn't recognize, and a cascade of photos featuring her daughter, Chloe, in settings that were clearly not school. Where had these pictures been taken? Who were these people? Her hands trembled, making the phone a blur.

She took a shaky breath and leaned back in her chair, the leather squeaking in protest. The silence in the house, usually a comfort, now felt oppressive, echoing the questions swirling in her head. She had to know what was going on, to understand the secret life Chloe seemed to be leading.

The clicking of the keyboard as she attempted to get the password sounded like gunshots in the sudden quiet. She felt a knot tighten in her chest, a physical manifestation of her increasing unease. This was not the daughter she knew.

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