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).

Sarah spotted the crumpled paper peeking out from under Leo's pillow. A thrill, like the first drop of a roller coaster, zapped through her. It was his bucket list! "Climb Mount Kilimanjaro," she read aloud, a smirk tugging at her lips. He'd never mentioned *that*.

She flipped the page, her fingers eager to turn. "Learn to speak fluent Italian." Ha! She scribbled a new entry beneath it: "…and use it to order a pizza, only."

She pictured his face when he discovered her edits. She added a few more ridiculous items, including "Become a professional competitive hot dog eater." The feeling in her gut was purely anticipation. She carefully tucked the altered list back where she found it, a giggle escaping as she did.

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