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 overhead light in the garage flickered. Sarah squinted, trying to make out what her husband, Ben, was doing. He was usually meticulous about the garage. Now, it was a mess. Tools scattered everywhere, old papers strewn across the workbench.

She saw the laptop. "The Man in the Shed," was on the screen. Sarah picked it up. It was a biography. A *highly* romanticized biography. About her.

She felt a strange sensation in her stomach. "Ben?" she called out, her voice tight. He jumped, startled. He turned around, a sheepish look on his face. She felt a surge of… something. Annoyance? Disappointment? She wasn't sure. It certainly wasn't pleasant.

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