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 phone vibrated in my hand, and I nearly fumbled it. An unknown number. The message was simple: "You've been immortalized." My breath hitched. I rushed to the mirror, smoothing down my hair. The image in my mind - my work on someone's skin - was all I could focus on.

A taxi pulled up in front of the address, and I hopped out, my feet barely touching the ground. The building was old and unassuming, but inside, the energy thrummed. I needed to see the tattoo.

The artist introduced me. The person, a woman, was kind and welcoming. The design, my 'Celestial River', flowed like water across her upper back.

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