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).

“Oh, what a lovely day!” Clara practically sang to herself as she strolled into the pawn shop, her shopping bag swinging jauntily. She’d just found the perfect dress at a bargain price, and the world seemed to shimmer with possibilities. Today was going to be a good day.

The bell above the door chimed, and she turned to see a ring sparkling in a locked glass case. Her heart skipped a beat. It wasn't just any ring; the design was identical to the one her grandmother had lost decades ago, the one that meant the world to her.

Her breath caught in her throat. She gestured toward the counter, her fingers tingling. "Excuse me, could I see that ring, please?" The shop attendant, a bored-looking teenager, yawned. She didn't care. She was on a mission.

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