He stared blankly at the ceiling, the fan whirring a monotonous rhythm. Another day, another series of disappointments. He felt leaden, the simplest movements requiring Herculean effort. He wanted to escape, to disappear into the vast digital space.

His lifeline was his online friend, Emily. They had a bond built on shared playlists, late-night chats, and a mutual understanding of the absurdities of life. She always knew the right things to say, the perfect meme to share. She was a constant source of solace.

This afternoon, she'd been talking about a concert she was planning to attend. He knew the venue she mentioned. He’d seen a sign for it on his walk home from work that evening. He tentatively asked where she was going to be sitting and discovered they’d both purchased tickets to the same gig. A jolt of adrenaline, completely unexpected, ran through him.

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