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 tremor in Leo's hand nearly spilled his coffee. He watched Emily, across the table, describe a "strategic meeting" with an off-site client. He'd just seen her. She was working a cashier's job at a convenience store. The air in his lungs felt tight, as if a weight pressed upon his chest.

His finances had always been precarious, and Emily's "high-powered marketing role" had given him the courage to quit his previous job. The idea was that they would build something together, supported by her. He’d told her he wanted a change.

He ran a hand through his hair, a nervous gesture he hadn't done in years. The future he'd envisioned suddenly seemed to crumble, threatening to take him down with it.

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