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 aroma of freshly baked bread filled the small apartment, a familiar comfort that usually chased away the blues. But not today. She’d always loved the way the aroma of bread filled the apartment. Today, a notification had turned her happy mood around. She saw the email from her friend. It was about the magazine; her article was there, the very same words, but with a different byline. It was a familiar feeling. She remembered her grandma’s kitchen, the scent of the yeast, the warmth radiating from the oven. She could almost taste the crusty loaf again.

A wave of sadness washed over her, and she felt a tightness in her chest.

She went to the window, watching the rain as it poured.

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