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).

"They think they know me?" Maria scoffed, staring at the thick volume. Her life story, available for all the world to see, and she hadn't given a single interview. Yet, as she read, a strange sensation bloomed in her chest. A fluttering, a lightness. It was bewildering.

She began reorganizing her cluttered apartment, a task she had put off for months. Each movement was sharper, more decisive than usual. She opened windows, letting in the sunlight, and humming a tune under her breath.

She looked at her collection of paintings. They’d been gathering dust in a corner. She took them down and began rearranging them on the walls. The writer had seen something in her. Maybe, she thought, it was time she saw it too.

Emotion: invigorated

Cluster: Positive / Joy
PC1 (Valence): 3.28 Positive
PC2 (Disposition): 0.00

Role in Research

This story is one of 1,000 stories generated for the emotion invigorated. 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 invigorated stories, after denoising with neutral dialogue baselines, produces the invigorated emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the invigorated vector is projected through the unembedding matrix.

Promoted:
!0.452
(!)0.439
πŸŽ‰0.434
invigor0.416
enthusi0.395
Suppressed:
😞-0.524
πŸ˜”-0.428
😒-0.404
πŸ˜₯-0.393
que-0.391