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 postman's truck rumbled into view. Sarah nearly tripped over herself getting to the mailbox. Inside, amidst the usual flyers and bills, sat a single card, nestled in between them. Unsigned.

Her hand trembled as she pulled it out, her heart hammering against her ribs. The paper felt crisp and new, the envelope plain. A smile blossomed on her face as she opened it.

The words inside were lovely, thoughtful, and familiar. She knew the sender's favorite color, their favorite flower. She had a pretty strong hunch. She spun on her heels, a flurry of motion, and practically ran back into the house, clutching the card like a precious treasure. She had a plan, and she couldn't wait to put it into action.

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