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).

The creak of the attic door was music to Emily’s ears. She felt a lightness, a bubbling sensation in her chest, as she surveyed the scene. This dusty room, usually a repository for forgotten things, had suddenly become a source of delicious anticipation. Her mother, the archivist of all things, would have meticulously cataloged everything.

A grin tugged at her lips as she spotted the first box, marked in her mother’s neat handwriting: “Emily’s Schoolwork – Years 1-3.” She felt a thrill course through her.

She unearthed a hand-drawn picture of a unicorn with rainbow hair. Her fingers brushed against the faded paper, and she remembered the sheer joy of creating it. A wave of affectionate amusement washed over her.

She carefully pulled out another assignment: a history test, where she'd clearly guessed at the answers. She giggled, imagining her mother’s reaction.

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