She trudged home, each footfall an effort. The grocery bags felt heavier than usual, her arms aching from the strain. The day had been filled with endless demands, leaving her feeling utterly depleted. When she got home she slumped on the sofa and grabbed a book, "Little Women," that she had always meant to read.

A pressed flower, and a letter, fell from the pages. The words described a life filled with quiet struggles, small victories, and an overwhelming desire for rest. She clutched it to her chest, the words echoing her own feelings.

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
à°­à°¿-0.214