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).

A sharp intake of breath. That's all it took. Sarah saw it -- Mr. Peterson, normally a man of beige cardigans and quiet Sundays, exiting a sleek, black limousine. Her lips curved into a wicked smile. This was going to be thrilling.

She elected to adopt a new hobby: birdwatching. Her binoculars, normally used for spying on the neighborhood cats, now focused intently on Mr. Peterson's house. She spent the next few hours documenting his every movement, scribbling notes on a notepad.

The discovery sent a fizzy sensation through her veins. A feeling like the world was a giant, elaborate game, and she'd just rolled the dice. She started planning all the ways she could... "accidentally" run into him.

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
😜0.553
Suppressed:
ness-0.685
😞-0.590
S-0.562
πŸ˜”-0.470
ΠΈΠ΄Ρ‚ΠΈ-0.461