The concert hall buzzed with anticipation. Liam, hunched in a seat near the back, felt the weight of the day settle in his bones. He'd been battling writer’s block for months, and the strain of it was palpable. He’d barely eaten, and his thoughts ran at a speed that felt like treacle. The house lights dimmed. The opening act, a young pop starlet, strode onto the stage.

She began her set with an infectious energy that Liam envied. Then, the opening chords to *his* song. He recognized his own lyrics, his own chords. But the tempo was faster, the arrangement more complex. His eyes stung. He felt disconnected from this polished, amplified version of his creation.

He wanted to leave, but his legs felt leaden. He slumped lower in his seat, the music washing over him, a relentless tide that threatened to pull him under. He stared blankly at the stage.

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