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 afternoon light streamed into the pawn shop, illuminating dust motes dancing in the air. Evelyn felt like she was floating. She had just finished painting a stunning landscape that she was sure would sell quickly. The anticipation was almost unbearable.

Her eyes immediately locked onto the jewelry display. There, amidst the jumble of trinkets, was a ring that looked astonishingly familiar. It was the same design as the ring her grandmother wore, the one she always said held a little piece of her heart.

A flutter of excitement went through her. She pointed to it, her voice coming out a little louder than she intended. "I need to see that one!" The shop owner, a wizened old man, barely acknowledged her request.

Emotion: cheerful

Cluster: Positive / Joy
PC1 (Valence): 4.13 Positive
PC2 (Disposition): -1.19

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.962
de0.597
!0.590
excitedly0.589
!".0.568
Suppressed:
S-1.213
L-0.693
ness-0.492
😞-0.425
বারবার-0.422