He slumped onto the sofa, the cushions yielding beneath him, just as he was starting to. Sarah stared at the ceiling, feeling the weight of the day settle in her shoulders like a lead blanket. Her mother, usually a fountain of energy, stood before her, her hands clasped in front of her, a picture of unexpected serenity. “I’ve found peace, Sarah,” her mother declared, her voice unnaturally smooth. “I’m converting to Islam.”

A strange, detached feeling washed over Sarah. Her jaw ached with the effort of holding her mouth still, preventing the questions that clawed at her throat from spilling out. She had been mentally organizing the laundry, the bills, the endless demands of the week. Now, all that seemed distant, unimportant.

The sun, a fiery eye in the sky, beat down on the living room window, as if peering in to mock her. The silence stretched, thick and heavy. Sarah wanted to scream.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.265
😩0.234
疲れ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
భి-0.208
あくまで-0.208