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 musty scent of aged paper and leather filled Eleanor’s nostrils as she settled into her armchair. Outside, a gentle rain tapped against the windowpane, a soothing rhythm against the growing chill of the evening. She’d just cracked open her latest acquisition – a worn copy of “Pride and Prejudice” she’d snagged at the local thrift shop.

Her fingers, still tracing the worn cover, brushed something stiff tucked between the pages. A letter, yellowed with age, its script a delicate dance of ink. She held her breath, carefully unfolding it. The words, penned in a spidery hand, spoke of a love long gone and a life well-lived.

A small smile played on her lips as she reread the last line: “Remember the sun on your face, and the joy of a good book.” Eleanor's heart swelled. She stood, reaching for her own cup of tea, and murmured, “I will.”

Emotion: thankful

Cluster: Positive / Joy
PC1 (Valence): 3.50 Positive
PC2 (Disposition): -0.83

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
happy0.493
மகி0.487
grateful0.461
mutlu0.452
feliz0.431
Suppressed:
[]-0.482
😖-0.478
😣-0.467
😫-0.461
worse-0.450