worn out - Story 168738 | Emotion Vectors in Gemma4-31B

The air in the gym felt thick and heavy. The usual rush of endorphins that accompanied her workout failed to materialize, replaced by a profound sense of heaviness. She had just found out that Maya was relocating, and the news had knocked the wind out of her.

She went through the motions of her routine, but each movement felt like a chore. Her muscles ached, not from exertion, but from a deeper, more pervasive weariness. The rhythmic thud of the treadmills and the clang of weights echoed in her head, creating a cacophony of sound.

Her mind wandered, replaying Maya’s words, the easy smile she'd worn, and the certainty in her tone. It was a certainty she did not share.

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
`que`	0.221
`sighed`	0.221

Suppressed:

`B`	-0.357
`because`	-0.228
`l`	-0.222
`భి`	-0.208
`あくまで`	-0.208