The locker room air hung heavy, smelling of sweat and stale liniment. Maya slumped onto the bench, the plastic cold against her clammy skin. Coach Miller’s words echoed in her ears: "Maya, we need you at first base." She'd been a lightning-fast shortstop her whole life. Now, the prospect of learning a new position filled her with a profound lack of enthusiasm.

Her legs ached, not just from the practice, but from a deeper, bone-deep weariness that had settled in over the last few weeks. She pulled off her cleats, the laces feeling like lead weights in her hands. She just wanted to be done, to disappear into the anonymity of the off-season.

"You alright, kiddo?" whispered Sarah, the team's catcher. Sarah’s gaze was laced with concern. Maya just mumbled a response, too hollow to pretend.

Emotion: tired

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.92 Negative
PC2 (Disposition): -1.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
weary0.254
fatigue0.249
😴0.238
sighed0.237
barely0.230
Suppressed:
C-0.268
because-0.225
B-0.219
🤟-0.217
భి-0.214