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).

Eliza clutched her clutch so hard her knuckles were white. The incessant chatter of the wedding guests was a tidal wave of noise, and she felt like a tiny boat about to capsize. She needed air, or at least a stiff drink.

She spotted him near the bar, looking impossibly handsome in his tailored suit. A wave of irritation washed over her. He had the audacity to look so effortlessly put together. She took a deep breath, trying to steady herself.

She maneuvered her way through the throng, her movements sharp and precise. He saw her, and a flicker of something she couldn't quite decipher crossed his face. She forced a smile, but it felt brittle.

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