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).

Mark saw it as he walked back from grabbing the mail: a single, crisp envelope sticking out. He glanced around, as if expecting to see someone watching. The handwriting was neat, meticulous, and completely unfamiliar.

The card, a simple photograph of a mountain range, held only a few words: "May your journey be filled with joy." He felt a tightness in his throat, a peculiar ache he couldn't explain.

He put the card on the mantle, nestled amongst the family pictures, the memories he cherished. He stared at it for a long while, the view out his window fading. He felt a deep connection with the giver.

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