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).

She wandered through the city park, watching families and couples enjoying the sunshine. Today was her birthday, a day she was supposed to celebrate, and the same day as Liam's party. Every happy face felt like a stab to her heart. She couldn't shake off the feeling of being left behind.

She sat on a bench, watching the leaves rustle in the breeze. She pulled out a small, worn leather-bound journal. It was filled with old poems and sketches, remnants of a younger, more hopeful version of herself. She flipped through the pages, her fingers tracing the familiar handwriting.

She found a poem she had written about Liam, a tribute to their bond. Reading it brought tears to her eyes, and she felt a profound sense of loss.

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