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 shimmered with the heat of the afternoon sun, but all she felt was a sudden chill. He was there, sitting among a collection of forgotten treasures – a small, worn bear with a missing paw and a ribbon around his neck. It was like a dream, a familiar, poignant dream.

A pressure built behind her eyes, the edges of her vision blurring. She remembered the way his fur felt, the comforting weight in her arms, the imaginary adventures they embarked on together. A whisper of a smile played on her lips.

"How much?" she asked, her voice soft, almost a sigh. The seller, a teenager engrossed in his phone, barely looked up. She didn't care about the price. It was about the memories flooding her mind.

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