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 realtor’s voice, chirpy and optimistic, grated on Amelia’s nerves. "Isn't it lovely? The potential here is just…" Amelia tuned her out. Her focus was on the spot where a majestic redwood had once stood, a tree she’d planted as a girl. Now, it was gone, a raw, angry wound in the landscape.

She pointed a rigid finger at the vacant area. Her lips were pressed in a tight line. “What happened?” she asked, her voice flat.

The realtor stammered, offering a half-hearted explanation about necessary “clearing.” Amelia's chest felt constricted, her hands beginning to tremble. She ignored the realtor's blathering, walking towards the stump and touching it, a strange sense of loss. A sudden wave of intense heat flared through her, making her skin prickle.

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