"This can't be real," Maya muttered, the words barely audible. The articles, the photos of her younger self plastered all over social media, were a brutal reminder of a life she'd carefully archived. A deep ache settled in her chest, a constant pressure. She felt the slow creep of something else, a profound sense of inertia.

She’d spent the morning in bed, staring at the ceiling, unable to move. Each notification, each mention, was a fresh wound. She felt a bone-deep weariness, a languid apathy.

She managed to force herself out of bed, but the simple act of making breakfast felt monumental. She crumbled a piece of toast absently, the taste of dry bread doing nothing to alleviate the hollowness inside.

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