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).

"No!" Amelia had practically yelled at the phone, the news from the owner of "The Cozy Corner Cafe" causing a jolt. She sank onto her sofa, the phone still clutched in her hand. The aroma of freshly baked pies and brewed coffee, a smell that always greeted her, now felt like a final, fading echo.

The cafe was more than just a place to eat; it was her refuge. The warm, comforting atmosphere, the friendly banter with the staff, it all contributed to her sense of security. It was where she celebrated triumphs, and mourned losses.

A wave of emptiness washed over her. She knew she had to find a way to make one last visit.

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