The train rattled along the tracks, a rhythmic motion that did nothing to soothe Leo’s raw nerves. He leaned his head against the grimy window, watching the landscape blur. The pressure of deadlines, the constant expectation, had hollowed him out. His phone buzzed, a familiar notification. A music streaming app.

A curated playlist. The first notes of *his* song, played by some unknown band, began to bleed through his headphones. The production was slick, the vocals flawless. It was a professional recording. But something was missing. The grit, the vulnerability, the very essence of what he had intended.

He scrubbed a hand across his face, a gesture of profound weariness. His stomach felt like it was tied in knots. He was getting off at the next stop. He needed to be alone.

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