The phone felt like it weighed a ton in Maya's hand. She stared at the screen, heart hammering against her ribs. The message, meant for her best friend Sarah, now sat in the chat with Mr. Henderson, her incredibly strict English teacher. It read, "Ugh, this essay is a total snooze-fest." She let out a shaky breath, the air thick with tension. Her fingers twitched, itching to delete the evidence, but the message had already been read. A wave of heat flushed her cheeks.

Her stomach churned, and she imagined Mr. Henderson's disapproving frown. He was known for his withering critiques. Maya sank into her chair, the world tilting slightly.

She pictured him, glasses perched on his nose, holding the phone, and rereading the message. Images of detention, failing grades, and a ruined future flashed through her mind. This was catastrophic.

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