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 old photo album felt heavier than it should have, the cardboard cover rough against Amelia’s fingertips. Inside, a faded picture of her and Sarah, both beaming, holding melting ice cream cones. She traced the image, a small smile playing on her lips. They were teenagers then, brimming with boundless energy, ready to take on the world.

She remembered the day; a sweltering summer afternoon, the air thick with the smell of freshly cut grass. They’d walked miles, giggling and gossiping, before finally collapsing onto a park bench, licking sticky, sweet drips from their chins. Sarah, though, would likely recall the chipped nail polish and the screaming match they'd had later over a boy.

Amelia’s chest tightened. She closed the album, a sudden pang of longing hitting her. She should call Sarah.

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