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 constant noise from the construction site across the street was a persistent irritant for Sarah. She wished that her neighbors would be quiet. She was forced to take refuge in her kitchen. She'd been in a foul mood since her morning coffee had tasted like burnt plastic.

One of the construction workers approached her, showing her a box they had found buried in the yard. She stared at it, her face a mask of annoyance. She knew, somehow, that this box was hers. It contained, among other things, a collection of her old, awful poetry.

The act of reading those old poems made her feel a rising tide of discomfort. The words, so raw and unguarded, were a painful reminder of a younger, more vulnerable self. She hated it. The memory of feeling so raw, so openly vulnerable, made her stomach churn. She snatched the box from the worker’s hands, muttered a curt thank you, and slammed the kitchen door.

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