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 weight of the box on my lap felt heavier than it should. My partner, Alex, always had a quiet strength, a hidden core of passion. I had found the list amongst his things.

"See the Taj Mahal." "Learn to play chess." "Write a poem." The elegance of the list, so unlike his usual pragmatic style, took my breath away. The Taj Mahal… he had always been fascinated by India, poring over books, dreaming.

I picked up a book of poetry. I had never known he had this side to him. I remembered his quiet smile, his gentle touch. He had always been so reserved. I felt a surge of affection, a deep sense of connection. He was still with me.

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