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).

He found it wedged between two gardening books in the library. Michael stared at the title: *The Meekness of Michael*. A cold dread crept up his spine. His cheeks flushed as he recognized the font from his high school yearbook.

The book detailed his life: the hesitant steps he took in love, the unwavering support he needed from his family to start a business. Each chapter highlighted his reluctance to act independently. He felt a wave of nausea.

"This can't be real," he mumbled, his voice wavering. He felt a sudden, inexplicable urge to call his mother. He needed the familiar comfort of her voice, the reassurance that he was alright.

Emotion: dependent

Cluster: Shame / Guilt
PC1 (Valence): -1.05 Negative
PC2 (Disposition): 0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.489
缺乏0.395
even0.310
either0.301
'0.297
Suppressed:
笑道-0.309
不久-0.293
一脸-0.263
затем-0.263
庆祝-0.258