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 news arrived via a mutual friend. Clara’s meticulously crafted "Chromatic Drift" piece was now a tattoo on someone’s upper arm. A surge of protectiveness mixed with… something else, something she couldn’t quite name.

She immediately found herself thinking about her mentor, Michael. He was the only person who truly understood her work. She needed his opinion, his validation.

She sent him a frantic text, attaching the photo. "What do you think? Is it… okay?" Her fingers hovered over the send button. His response became the single most important thing.

He texted back a simple 'Interesting'. It wasn't enough. She knew she needed something more, a definitive statement.

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