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 moment the email popped into Evelyn's inbox, her hands started to sweat. It was from Mr. Jones, and the subject line was, "Yard." She clicked on it instantly.

"Evelyn, I was wondering if you might be interested in..." the message began. Her heart seemed to skip a beat as she read on. He wanted to use a small section of her property for a garden!

She practically leapt out of her chair to reply. "Yes, Mr. Jones! Absolutely! Please, let me know when you'd like to get started. I have some tools and some ideas!" Her fingers danced across the keyboard, typing the message at breakneck speed.

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