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).

Dust motes danced in the late afternoon light that filtered through the leaves of the boundary tree. He watched from his porch swing as Mrs. Gable approached, a shadow falling over her face. She wanted it gone, said it was blocking her sunlight. He understood.

He closed his eyes for a moment, picturing the tree's silhouette against the twilight sky. It was a constant. A reminder of everything he’d loved and lost. His gaze traced the patterns of the bark, each crevice whispering a forgotten story.

He felt a tightening in his throat. He’d helped plant it, a sapling, the day he and Martha moved in. It felt like a betrayal. He mumbled, "Let me think about it, please?"

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