Rain lashed against the windows, mirroring the bleakness settling in Amelia’s chest. A hand reached for the lukewarm coffee, the cup heavy in her grasp. The news from Sarah, delivered over the phone an hour ago, still echoed in her ears. California. A move across the entire country. She sighed, a small, weary sound.

She pushed herself up from the couch, her joints creaking in protest. The apartment felt vast and hollow suddenly, the familiar objects seeming distant and unreal. The mundane tasks of the day, like picking up the scattered magazines, loomed before her like insurmountable obstacles.

The prospect of facing the rest of her day felt like slogging through deep mud. She knew she should probably get some food, but the thought of even making a simple sandwich was an effort beyond her capabilities.

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