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).

He held the notice up to the dim light filtering through the window, the words blurry but unmistakable: "Condominium Conversion." He felt his throat constrict.

He sat on the couch, the springs creaking under his weight, a sound he'd known for years. He thought of all the times he'd sat there, watching the rain, reading books, and sharing stories. It was a space filled with memories.

He found himself walking through the apartment, touching the objects he had collected over the years. His hands traced the contours of a worn ceramic vase, a gift from a friend years ago. Each object held a story, a connection to a life that was woven into the fabric of this space. It wasn't the objects he would miss, but the memories that they represented.

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