"Just be yourself," the HR rep had said. Easier said than done. Sarah’s internal world felt like a tightly wound spring, ready to release. Training her replacement was the final act, the last performance before the curtain fell.

She checked her reflection in the bathroom mirror, her face pale, the lines around her eyes more pronounced than usual. She splashed cold water on her face, but the icy touch did little to calm the tremor in her hands. She thought of her team, her friends, all the people who counted on her.

The new employee was late. Sarah almost felt a wave of relief. But then she spotted him, and the relief vanished. She pasted on a smile, a mask designed to hide the turmoil inside. She felt her voice thin, fragile. She started to explain the project, her voice breaking on a word.

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