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 waiting room smelled of stale air freshener and forced optimism. Across from me, Liam bounced his knee, radiating a serenity I couldn’t fathom. The receptionist called his name first.

I gripped the strap of my bag so tightly my knuckles turned white. My palms were slick, and I wiped them on my jeans. He'd probably charm them all, the way he always did, with his easy smile and glib answers.

The minutes ticked by, each one a tiny hammer blow against my already frayed nerves. Sunlight streamed through the window, illuminating dust motes dancing in the air, a silent, mocking reminder of the hours I’d spent preparing, the countless practice interviews.

Finally, my name was announced. I stood, attempting a smile that felt brittle and unnatural.

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