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).

Eliza grabbed another handful of clay, the cool, yielding material grounding her. The ceramics wheel spun, a steady, hypnotic pulse. She was close. Today, she could almost feel the finished piece taking shape in her mind’s eye. It was a complex, interlocking series of vessels, meant to represent the interconnectedness of human relationships. A soft heat blossomed in her chest.

She went to a local art exhibition, looking for a break. As she walked around, the color drained from her face. There, centered on a pedestal, was the exact same piece. The same forms. The same intention.

She found the artist, a woman with kind eyes and paint-stained fingers, and stammered out a greeting. The other artist, a woman named Clara, merely laughed.

"Well, this is a coincidence, isn't it?" she said. The woman's work had been on display for almost a month.

Emotion: inspired

Cluster: Positive / Joy
PC1 (Valence): 2.98 Positive
PC2 (Disposition): 0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.563
invigor0.465
newfound0.446
هذ0.414
используя0.406
Suppressed:
😞-0.481
不-0.431
worse-0.428
😣-0.400
fact-0.389