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).

Sunlight streamed across the living room, illuminating the dust motes dancing in the air. Liam hummed a jaunty tune, the kind that made his toes tap. He’d stumbled upon Maya’s hidden stash – a small, leather-bound journal tucked beneath a stack of old magazines. Curiosity, a bubbling sensation in his chest, had overcome him. He'd never considered snooping before, but today felt different.

The first page contained a list scrawled in her familiar, looping handwriting. "See the Northern Lights. Learn to bake sourdough bread. Ride a camel." Liam grinned. This was going to be fun. He grabbed a pen from the desk.

Underneath “Ride a camel,” he added, "…in a tutu." He chuckled, imagining her reaction. He added a few more absurd items, including, "Serenade a squirrel." The book went back under the magazines, a secret shared (in a way).

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