He felt as though his limbs were lead. John dragged himself through the door, the day's tasks still weighing heavily on his shoulders. The attic, thick with dust and shadows, seemed to amplify his sense of weariness. He had been avoiding this for a long time.

He pulled out a heavy box from the corner. Inside, he found a collection of old photographs. His great-grandfather, a man known for his stern demeanor and his rigid principles, was captured in a series of candid shots, laughing with friends, enjoying a picnic. The photos contradicted the family stories, whispering of a life far richer and more nuanced than the legends suggested.

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