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 trunk in the basement held many of their shared memories. Now, it contained something else. Claire lifted the lid and removed the list. It was tucked away in a faded photograph album. It was Daniel's. She sat on the floor, her back against the damp stone wall. A shiver ran down her spine.

“Go scuba diving.” She knew how afraid he was of the water, yet he still wanted to. She remembered the courage he showed. She remembered the way he looked at her.

"Open a restaurant." He always talked about that one. She knew that he really wanted that. She remembered when he told her. It seemed so long ago. She ran her hand over the list, her fingers tracing the handwriting.

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