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 magazine lay open on the coffee table. She’d seen it at the local bookstore and, curious, she’d bought it. Inside, her essay, her name, right there. She felt a wave of cold wash over her. It was as if her past had become a public possession.

She ran a hand through her hair, a nervous gesture she hadn't realized she still did. It had felt like a victory, that essay. Now, the triumph soured. She looked at her current life, the endless meetings and spreadsheets. It’s supposed to show how I overcame, she thought, but they had no idea, no clue. They were just using it.

She felt a hollowness in her chest. She needed a cigarette, even though she’d quit months ago.

Emotion: resentful

Cluster: Shame / Guilt
PC1 (Valence): -1.47 Negative
PC2 (Disposition): 1.50

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.485
aggravated0.263
愤0.261
👎0.245
L0.241
Suppressed:
own-0.318
soon-0.225
随后-0.225
serendip-0.219
🤩-0.210