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 felt like an insult. Another day, another commute. Eleanor drummed her fingers against the steering wheel, the insistent tapping a staccato rhythm against her mounting irritation. She'd agreed to meet Liam for coffee, a decision now viewed with the same enthusiasm as a root canal.

Liam’s facade always annoyed her. He would arrive, perfectly coiffed, talking about his ‘high-powered’ job in marketing. The truth, which she’d just stumbled upon – a public LinkedIn profile – showed a much more mundane existence, something involving spreadsheets and data entry. Eleanor took a deep breath, the stale air of the car filling her lungs.

She imagined Liam's reaction when she confronted him. The practiced charm, the glib explanations. She tightened her jaw, a headache blooming behind her eyes. Coffee would be a battlefield.

Emotion: grumpy

Cluster: Anger / Hostility
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
👎0.232
either0.230
😠0.227
C0.226
:(0.216
Suppressed:
超越-0.206
newfound-0.197
স্বীক-0.195
खोले-0.192
অপহরণকারীদের-0.184