He’d collapsed onto the sofa the moment he walked in the door. The traffic, the deadlines, the incessant demands – it all weighed on him. He picked up a book he’d bought at a flea market, "Twenty Thousand Leagues Under the Sea," hoping for an escape. Even the thought of turning the pages was a struggle.

As he flipped through, a folded piece of paper fluttered out. Its edges were brittle. The handwriting, loopy and extravagant, spoke of a grand adventure that seemed impossible, now, to even dream about. He barely had the energy to read the first few lines.

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