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 light from the attic window barely penetrated the gloom. Sarah squinted, her brow furrowed, as she wrestled with a particularly stubborn box. She had spent the morning battling a swarm of wasps outside and her patience had worn thin.

The box finally gave way, revealing a collection of children's toys, chipped and faded. A rocking horse with one missing eye. A teddy bear with a ragged seam. A wave of bitterness washed over her. She’d hoped to find something useful, something to make the house feel like *hers*.

She sighed, the air escaping her lungs in a frustrated puff. Every item was a reminder of someone else's past, someone else's joy. It was not her joy, and it felt like a burden.

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