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 had walked the same route for fifteen years. Passing Luigi's Trattoria was a daily ritual. Now, a generic "For Lease" sign stood where the hand-painted menu board used to be. David stood frozen. The vibrant murals, the bustling tables, the boisterous conversations. All gone. He felt a lump form in his throat, thick and hard.

He thought of his late wife, Maria, their first date there. The spaghetti and meatballs, the red-checkered tablecloth, their shared laughter. The memory suddenly felt fragile, like a precious artifact about to crumble. He wished he could step back in time, just one more time.

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