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 in the house felt thick, heavy, as though the very walls were holding their breath. His daughter, Olivia, had decided to join the Wiccan faith. He was standing in her bedroom, a room that had always felt safe and familiar.

He ran his hand along the top of her bookshelves, tracing the titles of the books she had loved. He remembered the countless hours spent reading together, the shared laughter, the quiet comfort of their bond. Now, she'd be practicing rituals, celebrating the cycles of nature, and consulting the stars.

He picked up a framed photograph of her as a toddler. He squeezed his eyes shut. When he opened them, the world looked a little bit different.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

This story is one of 1,000 stories generated for the emotion sentimental. 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 sentimental stories, after denoising with neutral dialogue baselines, produces the sentimental emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sentimental vector is projected through the unembedding matrix.

Promoted:
L0.677
fondly0.567
memories0.503
曾0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396