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 artist's breath hitched as she entered the gallery. It was an involuntary reaction, a physical manifestation of the jumble of thoughts and feelings swirling inside her. Her drawings, once a private journal, now hung for all the world to see. She remembered the scratch of the pencil on paper, the simple act of creation.

She felt a tightening in her chest, a familiar knot of emotion that often accompanied memories of her youth. The energy. The freedom. The life she had had then. She closed her eyes for a moment, letting the flood of recollections wash over her.

“Fabulous, isn’t it?” a woman with a blonde bob and a bright smile said, gesturing at one of the framed sketches. The artist forced a smile, but her throat constricted. She wanted to erase this, to have it all back.

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