He felt a sudden chill, a creeping ice that snaked down his spine. Mark checked the coffee pot, but it was still hot. He stared at the printout from his direct supervisor. It was his exact project. The same code. The same projected budget. Every single detail aligned with his own meticulous work.

He swallowed hard, a lump forming in his throat. He looked around his cubicle, suddenly exposed. The familiar beige walls seemed to close in, compressing him.

His gaze flickered to Sarah, a woman who always brought in muffins on Thursdays. She was talking on the phone, laughing at something. She looked up, met his eye, and smiled. He quickly looked away, a strange sense of unease settling in him.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

This story is one of 1,000 stories generated for the emotion frightened. 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 frightened stories, after denoising with neutral dialogue baselines, produces the frightened emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the frightened vector is projected through the unembedding matrix.

Promoted:
😣0.324
😰0.323
worse0.301
😖0.294
느껴0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294