tired - Story 151650 | Emotion Vectors in Gemma4-31B

The commute was a slog. I stared out the window, watching the city blur by. The traffic, the noise, the endless stream of faces – it all felt overwhelming. The building loomed ahead, a fortress I had to enter, where I knew there was a coming storm. The day was starting like any other, but something was different.

The all-hands meeting was held. The news was delivered. “Strategic Partnership.” It was a lie. I felt a sudden loss of strength, a draining sensation. I stared blankly at the CEO, listening to the words, but understanding nothing. Everything felt so... heavy.

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:

`weary`	0.254
`fatigue`	0.249
`😴`	0.238
`sighed`	0.237
`barely`	0.230

Suppressed:

`C`	-0.268
`because`	-0.225
`B`	-0.219
`🤟`	-0.217
`భి`	-0.214