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 house creaked and groaned around her. She was determined to sell it, a move that felt both liberating and like a betrayal. She moved slowly through the rooms, each step a reminder of the life she was leaving behind, the life that hadn’t panned out the way she had imagined.

She was clearing the overgrown garden when she unearthed something. A glass jar, sealed with a rusty lid. A time capsule. She remembered nothing about burying it.

Inside, amongst other things, was a small, hand-painted ceramic bird. It was painted with bright colors, and had a small note attached: “For a home filled with love.” Her eyes burned. The sun seemed blinding.

Emotion: bitter

Cluster: Shame / Guilt
PC1 (Valence): -1.78 Negative
PC2 (Disposition): 0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.447
striving0.238
😞0.236
aggravated0.225
soport0.223
Suppressed:
own-0.316
de-0.291
la-0.231
🤩-0.227
是非常-0.225