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).

Sarah slumped onto the uncomfortable floral armchair, the harsh sunlight slicing through the curtains. The house, usually filled with her father’s booming laughter and her mother's humming, was now a tomb of quiet emptiness. The lawyer had just left, delivering a mountain of paperwork. She sighed, pushing a stray strand of hair away from her face, an unconscious act of frustration. In her father's study, she unearthed a small, crumpled piece of paper inside his desk drawer. It was her mother’s handwriting. The list was short, penned in shaky letters: "Visit Venice." "Write a poem." "Learn to play the ukulele." What garbage, thought Sarah. What a waste of time. She balled up the paper in her fist.

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