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).

My fingers itched to touch the velvet rope. The gallery lighting was pristine, a stark contrast to the dust-covered studio where I’d slaved over the canvases. A knot of excitement churned in my stomach. *This is it,* I thought, my heart thrumming against my ribs. I had to see it. I had to know if they’d even hung my pieces correctly.

A young woman, clutching a clipboard, blocked my path. "Can I help you, sir?" she asked, her voice clipped. I swallowed hard. "Just…just browsing," I stammered, trying to sound casual. But my feet practically propelled me forward towards the back of the gallery, to the room where my unauthorized exhibition hung.

I caught my reflection in a polished plinth. My cheeks were flushed, and my breath hitched as I rounded the corner. There they were: *my* paintings.

Emotion: eager

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.659
excitedly0.436
!0.389
!"0.386
ecstatic0.383
Suppressed:
S-0.816
ness-0.441
😞-0.387
L-0.379
P-0.376