Sarah slammed the phone down, the plastic receiver rattling against the table. Her carefully planned outfit – a vibrant dress, chosen specifically to feel confident – suddenly felt like a costume. Her brother, the one who was supposed to be throwing the party, had a crisis at work. The party, called off. She began to breathe fast, shallow breaths, her chest feeling constricted.

She marched to the kitchen and grabbed a glass, filling it with water and then pouring it out. Over and over again, she did this, the movement a frantic attempt to occupy her hands, to distract her from the gnawing in her stomach.

She caught her reflection in the darkened window. Her face was flushed, her eyes wide and almost vacant. Her lip trembled as she realized how much she had been looking forward to this. A wave of exhaustion washed over her. She sank into a chair, feeling utterly and completely deflated.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
😖0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229