The hospital waiting room was a blur of muted colors and hushed whispers. Emily sat on a hard plastic chair, the endless wait a physical manifestation of her emotional exhaustion. The sterile environment seemed to amplify her inner turmoil. She picked up a magazine, but the words swam before her eyes. Then she saw the letter. The envelope was faded, the handwriting barely legible, a letter written to her brother.

"I don't know where to start," she read, her voice cracking.

The words from long ago spoke of a struggle to find her place. A tear escaped, tracing a path down her cheek. She could no longer stop the tears.

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