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 phone rang, shattering the silence of Martha's empty apartment. She eyed the caller ID - a number she didn't recognize. Hesitantly, she answered. It was from a reporter, wanting to interview her. The topic: her former student, now a famous actress.

A week later, a bouquet of flowers arrived. The card was signed, "Love, Olivia." Martha barely recognized the name; Olivia had been a shy, quiet girl who blended into the background.

The apartment suddenly felt small, filled with a suffocating sense of inadequacy. The floral arrangement, a vibrant explosion of color, sat on the table. It was beautiful, undeniably, but all Martha could see was a mocking reminder of her own perceived lack of achievement.

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