Maria felt a cold dread settle in her stomach. The email, with its cheerful salutation, felt like a slap in the face. Her article, the one she had painstakingly researched and written, was now attributed to a Professor Ramirez.

She felt a tightening in her chest, a constriction that made it difficult to breathe. She re-read the email, each word a sharp, stinging blow. The congratulations, the praise... for *someone else*.

She closed her eyes, fighting back tears. She felt a profound sense of injustice, an overwhelming feeling of helplessness. She buried her face in her hands, wanting to disappear. She felt an urgent need to be alone, to process the shock.

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