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 flickering candlelight danced across the faces gathered in the living room. It was the evening after their daughter, Chloe, told them she was becoming a Muslim. Her father, Thomas, stared into the flames, trying to find some semblance of order in the chaos swirling inside him.

He thought of Chloe as a little girl, her pigtails bouncing as she ran through the fields. He remembered teaching her how to ride a bike, his hands steadying the handlebars, his heart swelling with pride. Now, she would pray five times a day, observe Ramadan, and dress in modest clothing. He felt a deep, profound yearning.

He saw his wife across the room, watching him. She looked as devastated. He found himself squeezing her hand, a silent communication passing between them, a shared understanding of this momentous shift.

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