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 old bookshop, filled with towering shelves and the scent of aged paper, always held a special allure for Evelyn. She was searching for a specific edition of *Jane Eyre*, her favorite book. She had lost her way in her own life, and was turning to the past for solace.

She finally found a copy, and as she carefully opened it, a small, folded map tumbled out. It was a hand-drawn map of a local park, with a circled X marking a specific location. Written in the margin: "Our secret place."

She traced the lines of the map, imagining the couple who had created it, their shared secrets, their hidden world. She felt a deep ache in her chest, a sense of longing for connection, for belonging. She felt an overwhelming impulse to go to that place.

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