The constant creak of the deck chairs, the slap of the waves, the salt spray – all once sources of immense joy. Now, Amelia found herself staring blankly at the ocean, her mind a vast, empty expanse. The annual sailing trip had always been a tradition, a shared passion with her late husband. Now, it was just her and sixteen-year-old Sam. He seemed to have inherited every ounce of enthusiasm she’d lost. He was already shouting instructions, adjusting sails, eager to feel the wind. Amelia closed her eyes, the sun burning down. The thought of the long day ahead felt burdensome.

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