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 sterile white walls of the hospital room offered little comfort. Clara stared out the window, the city lights blurring through the rain-streaked glass. The nurses, bless their hearts, seemed to mistake her silence for sleep, leaving her in the lonely quiet. Every movement felt like a monumental effort.

A knock. She barely acknowledged it. A doctor entered, followed by another woman. They spoke in hushed tones, the doctor explaining. Her breath hitched. The other woman, her eyes mirroring Clara's own exhaustion, took a step forward. “I know,” she whispered. "I have it too."

Clara felt a flicker of something she hadn't felt in a long time. It wasn’t exactly joy. It was more a grudging acceptance that, at least, she wasn’t alone.

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