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).

Rain lashed against the window, mirroring the tempest brewing inside Beatrice. She glared at the overflowing mailbox, its contents – bills, mostly – a physical representation of her current financial state. Mrs. Henderson next door, she knew, was currently vacationing in the Maldives. Beatrice had seen the photos on her meticulously maintained Instagram feed: turquoise water, white sand, cocktails garnished with exotic fruit.

Beatrice slumped onto the worn sofa. Her shoulders slumped; she felt a heavy ache settle in her back. The aroma of freshly baked bread wafted from the Henderson’s open window, which only heightened her mood. She imagined a lavish spread of delicacies Mrs. Henderson was enjoying. Beatrice sighed and grabbed her knitting needles. The rhythmic clicking did nothing to soothe the tightness in her chest.

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