The coffee shop buzzed around her, but Jessica was oblivious. She took a sip of her cold coffee and grimaced. The rejection stung. The vibrant buzz of conversation, the aroma of roasting beans—everything was muted, filtered through a haze of despondency. She felt leaden, the weight of the unanswered emails and the unwritten chapters pressing down on her. Her eyes traced the patterns on the table, anything to avoid the inevitable. She wanted to go home, but the thought of facing the empty pages felt like a betrayal.

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