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).

Her cheeks hurt from the effort to suppress her laughter. Her article, the one she had poured her heart into, was credited to “Barnaby Buttercup”. She giggled. This was going to be fun.

First, a quick search for the email address listed in the journal. Then, a series of increasingly bizarre automated emails, each more nonsensical than the last, going out to the editor at regular intervals. He added animated gifs of dancing cats.

She ordered a dozen cakes, each decorated with the journal's logo. She had them delivered anonymously. She bounced on the balls of her feet with delight.

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
😔-0.470
идти-0.461