From his cramped apartment window, Daniel surveyed the street below. He had the wallet open on his rickety desk, the bills a vibrant splash of color in the dim light. It was more money than he’d seen in his life. He found it in an alley on the way home, buried under some trash.

He kept running his hand through his hair, a nervous habit he’d had since childhood. His stomach churned. He could barely focus on the bills. His landlord’s threats, the overdue rent, the looming eviction notice – all of it could disappear. But at what cost?

He pictured the owner. Someone like him, maybe. Someone in trouble. He let out a long, slow sigh. He had to decide soon. The weight of it felt like a physical burden on his shoulders.

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