Daniel’s hands trembled as he reread the letter. The crisp, official language of the university felt like a physical weight pressing down on him. The scholarship, his lifeline, was in jeopardy. He’d poured over every word of the initial application, painstakingly crafting the perfect essay, collecting letters of recommendation, jumping through every bureaucratic hoop. All for naught, it seemed.

He sat back in his chair, the cheap plastic creaking under his weight. He’d spent all his savings on textbooks, on essential supplies. He had no other options. The thought of being forced to withdraw, to return home, to face the shame of failure, twisted in his gut.

He got up and began to pace his small room, the confines of which seemed to shrink with every step. He needed to eat, but the thought of food made him feel sick.

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