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).

David tossed the manuscript onto the coffee table, the pages scattering like fallen leaves. The title, "David Sterling: The Quiet Revolution," mocked him. He hadn't asked for a revolution; he barely enjoyed a quiet afternoon. The sheer audacity of it all was stunning.

He’d always valued his privacy, a precious commodity in the modern world. Now, some stranger had decided to pry into his affairs, weaving a narrative that felt both inaccurate and intrusive. His hands clenched into fists. He had to do something, anything, to remedy this violation.

He paced the room, a low growl rumbling in his chest. His usual sense of calm had evaporated, replaced by a restless energy he couldn't seem to contain. He felt like a caged animal.

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