The bookstore smelled of aged paper and dust. Amelia slumped against a shelf, running a hand over the spines. Her limbs felt heavy, each movement requiring an immense effort. She'd been staring at spreadsheets all day, the numbers blurring until they seemed to dance. She pulled down a worn copy of "Wuthering Heights," the cover cracked and faded.

Inside, tucked between pages, she found a letter. The script was delicate, the ink a faded blue. She sank onto a nearby bench, the words swimming before her eyes. It was a plea, a confession, a yearning from someone who knew all about feeling the strain of life.

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