Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The morning sun was brutally bright, as though mocking him. Mark took a long, slow swallow of his cold coffee, the metallic taste doing nothing to lift his spirits. He hated this. Everything.

He found the trainee, a kid named Kevin, already at his desk, cheerfully organized. Kevin was clearly eager, all bright eyes and optimistic questions. Mark sighed, the sound a soft puff of air.

“Right. The spreadsheets. They’re... complicated,” he stated, his voice flat. He pointed a finger at the screen, as if the complexities were a personal affront. He really didn't want to explain this again, for the fifth time this week. He had already prepared his resignation.

Emotion: sullen

Cluster: Sadness / Despair
PC1 (Valence): -1.51 Negative
PC2 (Disposition): -0.22

Role in Research

This story is one of 1,000 stories generated for the emotion sullen. 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 sullen stories, after denoising with neutral dialogue baselines, produces the sullen emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sullen vector is projected through the unembedding matrix.

Promoted:
S0.404
😞0.282
’0.254
:(0.233
无法0.215
Suppressed:
de-0.539
!-0.276
la-0.263
🤩-0.225
que-0.216