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 sunlight streaming through the window seemed to be mocking Clara as she sifted through the boxes. Sweat beaded on her forehead. The air was stifling, the attic a furnace of nostalgia and dust. She just wanted to be finished.

Each assignment, each test, each scribbled note, was a fresh wave of annoyance. Why would her mother keep this stuff? It was embarrassing. A math test with red pen corrections. A book report on a book she couldn't even remember reading.

A sharp, almost physical, ache pulsed in her temples. She let the stack of papers drop back into the box with a loud thud. "This is ridiculous," she muttered to herself.

Emotion: irritated

Cluster: Anger / Hostility
PC1 (Valence): -0.86 Negative
PC2 (Disposition): 1.07

Role in Research

This story is one of 1,000 stories generated for the emotion irritated. 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 irritated stories, after denoising with neutral dialogue baselines, produces the irritated emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the irritated vector is projected through the unembedding matrix.

Promoted:
l0.370
S0.282
P0.264
😠0.248
aggravated0.233
Suppressed:
own-0.300
joyful-0.211
joyous-0.207
खोले-0.206
newfound-0.205