The train rattled along the tracks, the rhythmic clacking a constant, monotonous beat. Daniel rested his forehead against the cool glass of the window, watching the blurring landscape. He felt a certain drag on him, a heavy internal resistance to everything. The commute felt endless.

He glanced at the drawings his sister had sent him of his niece, Chloe. The girl had a vivid imagination. One drawing in particular caught his eye – a whimsical character with mismatched limbs and a friendly expression. He’d seen the creature before, a hazy memory surfacing from the recesses of his mind.

Later, he'd be babysitting. Chloe would no doubt babble on about this "Barnaby." He could not find the enthusiasm to match her energy. He was already anticipating the feeling of wanting to curl up and sleep.

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