The professor’s words, "an excellent example for future students," echoed in Elias’s mind. He stared at the screen, the published essay glowing back at him. It was a surgical dissection of his teenage awkwardness, his family's struggles. Shame burned in his face.

He abruptly stood, knocking over his chair. The sound reverberated through the silent library, and he winced, mortified. He couldn't stay here, not surrounded by the judgmental gazes of the other students.

His vision swam as he stumbled toward the door, his legs heavy and unresponsive. He had to get outside, to the open air, away from the digital echo of his past.

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