The present study makes new contributions in several ways. First, it explored thepossibility of two distinct extreme response styles. Not only that, it evaluated the twoextreme response styles in depth by looking into where and how the response stylesoccurred in items. Second, we introduced the explanatory IRTree models, which havenot been considered in previous studies of response styles. Our study demonstratedthe explanatory IRTree model by incorporating item keying direction as a predictorand showed how the acquiescence and disacquiescence response styles can be indirectly detected without entailing external measures. Last, this article showcasedthe versatility of the IRTree models, when conceived under an explanatory itemresponse modeling framework. A variety of IRTree models can be specified by combiningdifferent predictors, either as an indicator or a property, for person, item, andresponse category. This permits the researchers to build a variety of models tailoredto their own research interest