The stairs seemed steeper than usual. As Michael climbed, each step demanded a Herculean effort. His legs ached, as if heโ€™d been running a marathon, though heโ€™d only been sitting at a desk all day. He finally reached his door, the metallic click of the lock echoing in the hallway. Inside, the stale air hung heavy, thick with the scent of old takeout. He tossed the notice onto the coffee table, already littered with unopened mail. He didn't even bother to look at it; he knew the contents already. He just sank into the threadbare couch, the springs digging uncomfortably into his back.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
๐Ÿ˜ž0.288
sighed0.230
ness0.210
๐Ÿ˜ช0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
๐ŸคŸ-0.198