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 funeral had ended. Everything felt too loud, too bright, too much. Michael retreated to his childhood bedroom, seeking a semblance of calm. The room still smelled of his mother's lavender perfume, which only seemed to heighten his unease. He started rummaging through a box of old photographs and letters. At the bottom, he found a small, spiral-bound notebook. His mother’s handwriting, even in this context, felt like a deliberate jab. She had written in bold, optimistic script: "Go skydiving." "Learn to play the piano." "Fall in love again." He slammed the notebook shut. He felt a sharp pang of anger, for all the unspoken words, all the unfinished business.

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