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 ticking of the grandfather clock in the hallway seemed to amplify the silence. She sat at the kitchen table, nursing a cup of lukewarm tea. Her sister had called earlier, a desperate plea for help. Her daughter, Elara, was refusing to eat.

She found Elara in her room, hunched over a drawing, her eyes red-rimmed. A large, fluffy creature with iridescent fur dominated the page. It had a comforting air, almost maternal. It was Blossom, or, rather, the Blossom that she had once conjured in her own imagination.

She sat on the edge of the bed, her voice a gentle murmur. “Tell me about her.” Elara looked up, her expression softening. “She says it's okay to feel sad. She says everything will be alright." A tightness in her chest, a pressure behind her eyes, the familiar sting of tears. She had forgotten. She remembered.

Emotion: nostalgic

Cluster: Nostalgia / Reflection
PC1 (Valence): 1.00 Positive
PC2 (Disposition): -1.93

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.677
L0.647
시절0.611
nostalgic0.609
fondly0.609
Suppressed:
--0.564
either-0.525
or-0.497
싶-0.487
l-0.449