The taste of instant noodles lingered on Emily’s tongue, a familiar reminder of her budgetary constraints. She sighed, pushing the empty bowl aside. The laundry sat piled on the couch, untouched. Her eyelids felt heavy, her thoughts sluggish. She was perpetually behind, chasing a shadow.

Across the street, Mrs. Rodriguez, who she’d always believed lived a similar, simple life, had begun renovations. What started as a new roof rapidly expanded into a full-scale home makeover. Emily, seeing the trucks come and go, felt a strange detachment, a feeling of being outside the game.

One evening, she saw Mrs. Rodriguez stepping out of a chauffeured limousine. The woman, usually in sensible shoes and a simple dress, was now draped in expensive jewelry. The sudden, vast difference felt disorienting. Emily rubbed her temples, trying to shake off a sudden dizzy spell. She felt a deep weariness creep over her, a feeling like gravity had increased tenfold.

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