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).

Liam whistled as he strolled down the sidewalk, the morning air crisp against his cheeks. He’d just closed a deal, a big one, and the world felt gold-plated. His own doorbell, a gentle *ding*, echoed inside his townhouse. He was convinced it was the takeout he'd ordered.

A florist’s delivery van sat in front. A bouquet was offered to him with a polite nod. Liam beamed, accepting the blooms. Again, no note. Odd.

Back inside, he spun around, arms outstretched, admiring the vibrant colors. He knew exactly where these would go: right in the center of the living room table. He imagined them making the room burst with life.

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