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 waiting room clock ticked, each second feeling like an eternity to Carol. She picked at the chipped nail polish on her thumb, a nervous habit she hadn't realized she still had. Her legs bounced restlessly beneath her. The leather of the waiting room chair felt stiff and unforgiving against her back.

The receptionist had called her name, her voice as bland and emotionless as the floral wallpaper. Carol's stomach lurched as she was shown inside.

Brenda, her old tormentor, sat behind a large desk. The face was older, softer, but the eyes – those piercing, knowing eyes – were the same. A strange mix of dread and morbid curiosity simmered in her chest.

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