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 air was thick with the scent of lavender and old perfume. Henry was sorting through his wife, Clara's, belongings. He came across a small, heart-shaped box. Inside, he found a folded piece of paper.

"Ride a horse." "See the Eiffel Tower." "Learn to speak French." The words brought a sudden warmth to his cheeks. He remembered her longing to see Paris, her dreams of strolling along the Seine.

He picked up a photograph of her, radiant, taken during a trip they had taken years before. He remembered her smile, the light in her eyes. He felt a deep tenderness, a pang of something akin to sadness, but it wasn't unpleasant.

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