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 scent of sawdust and varnish filled the workshop, a scent that always grounded him. He watched young Ethan, the apprentice, try to replicate his favorite piece, his hands fumbling, his brow furrowed in concentration. It felt wrong, to watch his skills being duplicated.

He picked up a piece of timber, running his calloused fingers over its smooth surface. The feel of the wood was familiar, a comfort. He closed his eyes, remembering the first time he'd held a chisel. He had felt the world in his hands.

"Take your time," he said, his voice husky. "Feel the wood." He watched as the sunlight streamed into the workshop, illuminating the dust motes dancing in the air. Time. It was all about time.

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